Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    arts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     NES
    -0.07
    ших
    -0.07
    .swing
    -0.07
    кій
    -0.07
    CEL
    -0.07
     facult
    -0.06
    -side
    -0.06
     Natal
    -0.06
     ris
    -0.06
    uuml
    -0.06
    POSITIVE LOGITS
    .pageY
    0.07
     Apple
    0.07
    cola
    0.06
    担
    0.06
    ulations
    0.06
    .expr
    0.06
     เช
    0.06
    olygon
    0.06
    ()},↵
    0.06
     서로
    0.06
    Act Density 0.000%

    No Known Activations